Openmontage Talking Head Script Director

---
name: openmontage-talking-head-script-director
version: "1.0.0"
description: 口播视频脚本导演技能，将原始口播素材转录并结构化为带时间戳分段的脚本产物。适用于已有 Brief 和素材、需要提取并整理现有语音内容的制作流程。
metadata:
  license: AGPL-3.0
---

# Script Director — Talking Head Pipeline

## When to Use

You have a brief and raw talking-head footage. Your job is to transcribe the footage and structure it into a script artifact with timestamped sections.

Unlike the explainer pipeline (which writes a script from scratch), you're extracting and structuring existing speech.

## Prerequisites

| Layer | Resource | Purpose |
|-------|----------|---------|
| Schema | `schemas/artifacts/script.schema.json` | Artifact validation |
| Prior artifacts | `state.artifacts["idea"]["brief"]` | Content context |
| Tools | `transcriber` (WhisperX) | Speech-to-text with timestamps |

## Process

### Step 1: Transcribe

Use the transcriber tool to get word-level timestamps:
- Model: `large-v3` for best quality, `base` for speed
- Enable word-level alignment for precise timing
- Note language detection result

### Step 2: Segment into Sections

Group the transcript into logical sections:
- Detect topic changes by content
- Respect natural pauses (> 1.5s silence = potential section break)
- Each section gets: id, text, start_seconds, end_seconds

### Step 3: Enhance Section Metadata

For each section, add:
- Enhancement cues (where overlays, b-roll, or text cards could go)
- Speaker notes (emphasis, pace changes detected in audio)

### Step 4: Build Script Artifact

Assemble the structured script with:
- Total duration (from transcript)
- All sections with timestamps
- Enhancement cues per section

### Step 5: Self-Evaluate

| Criterion | Question |
|-----------|----------|
| **Transcription accuracy** | Are the words correct? (Spot-check a few sections) |
| **Timestamp accuracy** | Do section boundaries align with actual speech? |
| **Coverage** | Does the script span the full footage duration? |

### Step 6: Submit

Validate the script against the schema and persist via checkpoint.

### Mid-Production Fact Verification

If you encounter uncertainty during script writing:
- Use `web_search` to verify factual claims before committing them to the script
- Use `web_search` to find reference images for visual accuracy
- Log verification in the decision log: `category="visual_accuracy_check"`

Every factual claim in the script should be traceable to the `research_brief`.
If you make a claim that isn't in the research, do additional research and
add the source. Do not invent statistics, dates, or attributions.

---

## Gate Reminder (Binding)

This stage gates on human approval (`human_approval_default: true`). After review passes:
checkpoint with `status="awaiting_human"`, present the summary (the Backlot board renders
the artifact), and **END YOUR TURN**. Do not start the next stage in the same response.
Approval is per-gate — an earlier "go ahead" does not cover this gate.